SimTriplet: Simple Triplet Representation Learning with a Single GPU
- URL: http://arxiv.org/abs/2103.05585v1
- Date: Tue, 9 Mar 2021 17:46:09 GMT
- Title: SimTriplet: Simple Triplet Representation Learning with a Single GPU
- Authors: Quan Liu, Peter C. Louis, Yuzhe Lu, Aadarsh Jha, Mengyang Zhao,
Ruining Deng, Tianyuan Yao, Joseph T. Roland, Haichun Yang, Shilin Zhao, Lee
E. Wheless, Yuankai Huo
- Abstract summary: We propose a simple triplet representation learning (SimTriplet) approach on pathological images.
By learning from 79,000 unlabeled pathological patch images, SimTriplet achieved 10.58% better performance compared with supervised learning.
- Score: 4.793871743112708
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Contrastive learning is a key technique of modern self-supervised learning.
The broader accessibility of earlier approaches is hindered by the need of
heavy computational resources (e.g., at least 8 GPUs or 32 TPU cores), which
accommodate for large-scale negative samples or momentum. The more recent
SimSiam approach addresses such key limitations via stop-gradient without
momentum encoders. In medical image analysis, multiple instances can be
achieved from the same patient or tissue. Inspired by these advances, we
propose a simple triplet representation learning (SimTriplet) approach on
pathological images. The contribution of the paper is three-fold: (1) The
proposed SimTriplet method takes advantage of the multi-view nature of medical
images beyond self-augmentation; (2) The method maximizes both intra-sample and
inter-sample similarities via triplets from positive pairs, without using
negative samples; and (3) The recent mix precision training is employed to
advance the training by only using a single GPU with 16GB memory. By learning
from 79,000 unlabeled pathological patch images, SimTriplet achieved 10.58%
better performance compared with supervised learning. It also achieved 2.13%
better performance compared with SimSiam. Our proposed SimTriplet can achieve
decent performance using only 1% labeled data. The code and data are available
at https://github.com/hrlblab/SimTriple.
Related papers
- Scaling Backwards: Minimal Synthetic Pre-training? [52.78699562832907]
We show that pre-training is effective even with minimal synthetic images.
We find that a substantial reduction of synthetic images from 1k to 1 can even lead to an increase in pre-training performance.
We extend our method from synthetic images to real images to see if a single real image can show similar pre-training effect.
arXiv Detail & Related papers (2024-08-01T16:20:02Z) - Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction [153.52406455209538]
Gamba is an end-to-end 3D reconstruction model from a single-view image.
It completes reconstruction within 0.05 seconds on a single NVIDIA A100 GPU.
arXiv Detail & Related papers (2024-03-27T17:40:14Z) - Splatter Image: Ultra-Fast Single-View 3D Reconstruction [67.96212093828179]
Splatter Image is based on Gaussian Splatting, which allows fast and high-quality reconstruction of 3D scenes from multiple images.
We learn a neural network that, at test time, performs reconstruction in a feed-forward manner, at 38 FPS.
On several synthetic, real, multi-category and large-scale benchmark datasets, we achieve better results in terms of PSNR, LPIPS, and other metrics while training and evaluating much faster than prior works.
arXiv Detail & Related papers (2023-12-20T16:14:58Z) - SimMatchV2: Semi-Supervised Learning with Graph Consistency [53.31681712576555]
We introduce a new semi-supervised learning algorithm - SimMatchV2.
It formulates various consistency regularizations between labeled and unlabeled data from the graph perspective.
SimMatchV2 has been validated on multiple semi-supervised learning benchmarks.
arXiv Detail & Related papers (2023-08-13T05:56:36Z) - Joint one-sided synthetic unpaired image translation and segmentation
for colorectal cancer prevention [16.356954231068077]
We produce realistic synthetic images using a combination of 3D technologies and generative adversarial networks.
We propose CUT-seg, a joint training where a segmentation model and a generative model are jointly trained to produce realistic images.
As a part of this study we release Synth-Colon, an entirely synthetic dataset that includes 20000 realistic colon images.
arXiv Detail & Related papers (2023-07-20T22:09:04Z) - Is Cross-modal Information Retrieval Possible without Training? [4.616703548353372]
We take a simple mapping computed from the least squares and singular value decomposition (SVD) for a solution to the Procrustes problem.
That is, given information in one modality such as text, the mapping helps us locate a semantically equivalent data item in another modality such as image.
Using off-the-shelf pretrained deep learning models, we have experimented the aforementioned simple cross-modal mappings in tasks of text-to-image and image-to-text retrieval.
arXiv Detail & Related papers (2023-04-20T02:36:18Z) - Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image
Retrieval [51.42470171051007]
This paper tackles the Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) problem from the viewpoint of cross-modality metric learning.
By combining two fundamental learning approaches in DML, e.g., classification training and pairwise training, we set up a strong baseline for ZS-SBIR.
We show that Modality-Aware Triplet Hard Mining (MATHM) enhances the baseline with three types of pairwise learning.
arXiv Detail & Related papers (2021-12-15T08:36:44Z) - QK Iteration: A Self-Supervised Representation Learning Algorithm for
Image Similarity [0.0]
We present a new contrastive self-supervised representation learning algorithm in the context of Copy Detection in the 2021 Image Similarity Challenge hosted by Facebook AI Research.
Our algorithms achieved a micro-AP score of 0.3401 on the Phase 1 leaderboard, significantly improving over the baseline $mu$AP of 0.1556.
arXiv Detail & Related papers (2021-11-15T18:01:05Z) - Contrastive Learning Meets Transfer Learning: A Case Study In Medical
Image Analysis [2.4050073971195003]
Annotated medical images are typically rarer than labeled natural images since they are limited by domain knowledge and privacy constraints.
Recent advances in transfer and contrastive learning have provided effective solutions to tackle such issues from different perspectives.
It would be appealing to accelerate contrastive learning with transfer learning, given that slow convergence speed is a critical limitation of modern contrastive learning approaches.
arXiv Detail & Related papers (2021-03-04T17:19:54Z) - Fed-Sim: Federated Simulation for Medical Imaging [131.56325440976207]
We introduce a physics-driven generative approach that consists of two learnable neural modules.
We show that our data synthesis framework improves the downstream segmentation performance on several datasets.
arXiv Detail & Related papers (2020-09-01T19:17:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.